-
AmberYifan/qwen2.5-7b-instruct-full-pretrain-control-tweet-1m-en-sft
Text Generation • 8B • Updated • 5 -
AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft
Text Generation • 8B • Updated • 4 • 1 -
AmberYifan/qwen2.5-7b-instruct-full-pretrain-mix-high-tweet-1m-en-sft
Text Generation • 8B • Updated • 5 -
AmberYifan/qwen2.5-7b-instruct-full-pretrain-mix-mid-tweet-1m-en-sft
Text Generation • 8B • Updated • 4
Yifan Wang
AmberYifan
AI & ML interests
None yet
Recent Activity
updated a model about 6 hours ago
AmberYifan/qwen3-4b_openrubrics_v2_grpo_structure_only_kmeans_step60 published a model about 6 hours ago
AmberYifan/qwen3-4b_openrubrics_v2_grpo_structure_only_kmeans_step60 updated a model about 10 hours ago
AmberYifan/llama3.2-3b-instruct_aime_grpo_structure_only_hybrid_adaptive_kmeansOrganizations
-
AmberYifan/qwen2.5-7b-instruct-full-pretrain-control-tweet-1m-en-sft
Text Generation • 8B • Updated • 5 -
AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-sft
Text Generation • 8B • Updated • 4 • 1 -
AmberYifan/qwen2.5-7b-instruct-full-pretrain-mix-high-tweet-1m-en-sft
Text Generation • 8B • Updated • 5 -
AmberYifan/qwen2.5-7b-instruct-full-pretrain-mix-mid-tweet-1m-en-sft
Text Generation • 8B • Updated • 4
Learning from Abundant User Dissatisfaction in Real-World Preference Learning
models 191
AmberYifan/qwen3-4b_openrubrics_v2_grpo_structure_only_kmeans_step60
4B • Updated
AmberYifan/llama3.2-3b-instruct_aime_grpo_structure_only_hybrid_adaptive_kmeans
4B • Updated
AmberYifan/llama3.2-3b-instruct_aime_grpo_accuracy_only
4B • Updated
AmberYifan/llama3.2-3b-instruct_openrubrics_grpo_structure_only_kmeans
4B • Updated • 32
AmberYifan/llama3.2-3b-instruct_aime_grpo_structure_only_kmeans
4B • Updated • 17
AmberYifan/capsdnum-marin-8b-base-science_cap_b8000_s0
Text Generation • 8B • Updated • 40
AmberYifan/capsdnum-marin-8b-base-science_random_b4000_s0
Text Generation • 8B • Updated • 48
AmberYifan/capsdnum-marin-8b-base-science_ppl_b4000_s0
Text Generation • 8B • Updated • 42
AmberYifan/capsdnum-marin-8b-base-science_cap_b4000_s0
Text Generation • 8B • Updated • 44
AmberYifan/capsdnum-marin-8b-base-science_random_b2000_s0
Text Generation • 8B • Updated • 38
datasets 28
AmberYifan/seed-data
Viewer • Updated • 491 • 29
AmberYifan/dsat-data
Viewer • Updated • 10.6k • 26
AmberYifan/sat-data
Viewer • Updated • 4.43k • 27
AmberYifan/mistral-v0.1-spin-hhrlhf
Viewer • Updated • 5.5k • 23
AmberYifan/sft-spin-filter
Updated • 9
AmberYifan/sft-spin-kcenter-5k
Viewer • Updated • 5.5k • 14
AmberYifan/gsm8k-sft
Viewer • Updated • 8.79k • 20
AmberYifan/sft-spin-v
Viewer • Updated • 50.5k • 32
AmberYifan/safeRLHF-SFT
Viewer • Updated • 83.4k • 27
AmberYifan/SPIN-trans-DPOformat
Viewer • Updated • 55k • 13